Use OmniHuman 1.5 through Rivya Public API v1 with model id omnihuman-1-5, supported inputs, parameters, Files API rules, credits, and response examples.

Available via APIReadinessVideo

API model id

omnihuman-1-5

Inputs

file

Files API

Required for reference modes

Base credits

per_input_second · default=27 · ⌈total⌉

Capability

Video

Billing

METERED

Prompt limit

300 characters

Request contract

Send the model id at the top level. Model-specific controls belong in params.

Key	Type	Required	Default	Description
model	string	Yes	omnihuman-1-5	Use the omnihuman-1-5 API model id.
prompt	string	No	-	Maximum 300 characters for this model.
params	object	No	-	Model-specific parameter object. Use the rows below for allowed keys.
client_request_id	string	No	-	Optional client-side id for tracing requests in your system.

Model parameters

Key	Type	Required	Default	Range	Options	Description
output_resolution	select	No	1080	-	720, 1080	Output resolution
pe_fast_mode	select	No	false	-	false, true	Choose a quality-first run or prioritize faster processing with a possible quality tradeoff.
seed	number	No	-1	-	-	Leave it empty for a new random result each time. Reusing the same integer makes it easier to reproduce or fine-tune a previous result. It stays closer only when the prompt and other key settings also remain similar, and it is not a guaranteed 1:1 match.

Upload policy

Upload reference files first, then place the returned URL and duration token inside params.referenceMediaItems.

Reference rule

Portrait image and audio: Upload exactly one JPEG, PNG, or WebP portrait up to 10 MB and one MP3, M4A, WAV, AAC, or OGG audio file up to 10 MB and under 60 seconds.

Max files

Accepted file kinds

image, audio

Duration token

Video and audio references should carry durationToken from /api/v1/files when duration verification is required.

kind	Max size	MIME types
image	10 MB	image/jpeg, image/png, image/webp
audio	10 MB	audio/mpeg, audio/mp4, audio/wav, audio/x-wav, audio/aac, audio/ogg

Minimal request

{
  "model": "omnihuman-1-5",
  "params": {
    "output_resolution": "1080",
    "pe_fast_mode": "false",
    "seed": -1
  }
}

Reference-file request

{
  "model": "omnihuman-1-5",
  "params": {
    "output_resolution": "1080",
    "pe_fast_mode": "false",
    "seed": -1,
    "referenceMediaItems": [
      {
        "url": "https://cdn.example.com/reference-image.png",
        "kind": "image",
        "name": "reference-image.png",
        "mimeType": "image/png",
        "width": 1024,
        "height": 1024,
        "sizeBytes": 1048576,
        "imageDimensionsToken": "image_dimensions_token_from_original_files_api_upload_response"
      },
      {
        "url": "https://cdn.example.com/reference-audio.wav",
        "kind": "audio",
        "name": "reference-audio.wav",
        "mimeType": "audio/wav",
        "durationSeconds": 12,
        "durationToken": "audio_duration_token_from_files_api"
      }
    ]
  }
}

Create response

The create endpoint returns a public task id. Poll the status endpoint until the task succeeds or fails.

{
  "id": "task_omnihuman_1_5_example",
  "status": "queued",
  "model": "omnihuman-1-5",
  "reserved_credits": 27,
  "final_credits": 0,
  "settlement_status": "RESERVED",
  "created_at": "2026-05-11T00:00:00.000Z",
  "updated_at": "2026-05-11T00:00:00.000Z",
  "result": null,
  "error": null
}

Common errors

validation_failed, insufficient_credits, idempotency_conflict, rate_limited, not_found

Some modes require Files API reference uploads.

OmniHuman 1.5 API Integration